Mesa (master): anv: Flush caches prior to PIPELINE_SELECT on all gens

[Jason Ekstrand]

Module: Mesa
Branch: master
Commit: 6baae9625d26d282a72481598f9431fcad3211f6
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=6baae9625d26d282a72481598f9431fcad3211f6

Author: Jason Ekstrand <jason at jlekstrand.net>
Date:   Wed Mar 15 11:58:52 2017 -0700

anv: Flush caches prior to PIPELINE_SELECT on all gens

The programming note that says we need to do this still exists in the
SkyLake PRM and, from looking at the bspec, seems like it may apply to
all hardware generations SNB+.  Unfortunately, this isn't particularly
clear cut since there is also language in the bspec that says you can
skip the flushing and stall to get better throughput.  Experimentation
with the "Car Chase" benchmark in GL seems to indicate that some form of
flushing is still needed.  This commit makes us do the full set of
flushes regardless of hardware generation.  We can always reduce the
flushing later.

Reported-by: Topi Pohjolainen <topi.pohjolainen at intel.com>
Reviewed-by: Iago Toral Quiroga <itoral at igalia.com>
Cc: "17.0 13.0" <mesa-stable at lists.freedesktop.org>

---

 src/intel/vulkan/genX_cmd_buffer.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/src/intel/vulkan/genX_cmd_buffer.c b/src/intel/vulkan/genX_cmd_buffer.c
index 5d923a8c08..d0ddc29f00 100644
--- a/src/intel/vulkan/genX_cmd_buffer.c
+++ b/src/intel/vulkan/genX_cmd_buffer.c
@@ -2133,8 +2133,8 @@ flush_pipeline_before_pipeline_select(struct anv_cmd_buffer *cmd_buffer,
     */
    if (pipeline == GPGPU)
       anv_batch_emit(&cmd_buffer->batch, GENX(3DSTATE_CC_STATE_POINTERS), t);
+#endif
 
-#elif GEN_GEN <= 7
    /* From "BXML » GT » MI » vol1a GPU Overview » [Instruction]
     * PIPELINE_SELECT [DevBWR+]":
     *
@@ -2160,7 +2160,6 @@ flush_pipeline_before_pipeline_select(struct anv_cmd_buffer *cmd_buffer,
       pc.InstructionCacheInvalidateEnable = true;
       pc.PostSyncOperation                = NoWrite;
    }
-#endif
 }
 
 void